Feng Wang
> Hi @FateScript , > > Does yolox not support the torch_hub library? It should support such feature. Any issue raised? Could you please paste your error log?
> assert targets is not None Plz add the following code. ```python model.eval() ```
> How can I fix? Not sure what's in your picture. From code your posted, I believe that you might need to `cv2.resize` image to size 640(this value is provided...
In my opinion, pre-trained yolox should resize image to 640 to maintain the consistency of training process and eval process. I'm not sure what the true purpose of changing it....
Label assign is also a dynamic process.
1. check if other code using DDP works on your machine. 2. If it could not working, try another version torch or check your hardware 3. If it works, try...
It's just a warning that shows your model has different shape with checkpoint. Don't worry about that.
You log says: `ERROR: Unexpected bus error encountered in worker. This might be caused by insufficient shared memory (shm).` Reduce the `data_num_workers` in exp might help you. 2 is suggested...
Plz install through pip but not hack `sys.path`.
Since you are finetuning YOLOX on customed dataset, did you evalutate your model on it?